© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2563
    Prev
    Next
    INDEX
    Explanations

    sports-related transfer player names and their associated fees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.06
    2:0.07
    3:0.09
    4:0.12
    5:0.05
    6:0.06
    7:0.06
    8:0.13
    9:0.03
    10:0.03
    11:0.18
    Negative Logits
    />
    -3.27
    :]
    -2.90
     eq
    -2.77
    >)
    -2.74
    }:
    -2.68
    >:
    -2.68
    conserv
    -2.63
     nodd
    -2.62
    pmwiki
    -2.60
     scen
    -2.60
    POSITIVE LOGITS
     Barcelona
    3.99
     Bethlehem
    3.78
     Buenos
    3.59
     Charlotte
    3.59
     Istanbul
    3.50
     Chelsea
    3.46
     Brazilian
    3.37
     Columbus
    3.37
     Madrid
    3.33
     José
    3.33
    Activations Density 0.003%

    No Known Activations